© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 202122
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_6_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    y
    1.54
    ।
    1.38
    i
    1.33
    at
    1.23
    。
    1.16
    '
    1.15
    p
    1.14
    al
    1.05
    t
    0.97
    b
    0.97
    POSITIVE LOGITS
     će
    0.92
    ин
    0.90
     መሳሪያ
    0.89
     ሂደት
    0.87
     predsjed
    0.87
     അറിയ
    0.86
    ことにより
    0.86
     በሽታ
    0.85
     svijet
    0.84
    ાઇન
    0.83
    Activations Density 0.000%

    No Known Activations